Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts
louisbrulenaudet
posted anupdate 2 days ago
view post
Post
1951
🚨 I have $3,500 in Azure credits, including access to an H100 (96 Go), expiring on November 12, 2024.

I won’t be able to use it all myself, so I’m reaching out to the @huggingface community: Are there any open-source projets with data ready for some compute power?

Let’s collaborate and make the most of it together 🔗
·
davidberenstein1957
posted anupdate 1 day ago
view post
Post
914
You can now build a custom text classifier without days of human labeling!

👍 LLMs work reasonably well as text classifiers.
👎 They are expensive to run at scale and their performance drops in specialized domains.

👍 Purpose-built classifiers have low latency and can potentially run on CPU.
👎 They require labeled training data.

Combine the best of both worlds: the automatic labeling capabilities of LLMs and the high-quality annotations from human experts to train and deploy a specialized model.

Blog:https://huggingface.co/blog/sdiazlor/custom-text-classifier-ai-human-feedback
reach-vb
posted anupdate about 12 hours ago
view post
Post
359
What a great day for Open Science! @AIatMeta released models, datasets, and code for many of its research artefacts! 🔥

1. Meta Segment Anything Model 2.1: An updated checkpoint with improved results on visually similar objects, small objects and occlusion handling. A new developer suite will be added to make it easier for developers to build with SAM 2.

Model checkpoints: reach-vb/sam-21-6702d40defe7611a8bafa881

2. Layer Skip: Inference code and fine-tuned checkpoints demonstrating a new method for enhancing LLM performance.

Model checkpoints: facebook/layerskip-666b25c50c8ae90e1965727a

3. SALSA: New code enables researchers to benchmark AI-based attacks to validate security for post-quantum cryptography.

Repo:https://github.com/facebookresearch/LWE-benchmarking

4. Meta Lingua: A lightweight and self-contained codebase designed to train language models at scale.

Repo:https://github.com/facebookresearch/lingua

5. Meta Open Materials: New open source models and the largest dataset to accelerate AI-driven discovery of new inorganic materials.

Model checkpoints: fairchem/OMAT24

6. MEXMA: A new research paper and code for our novel pre-trained cross-lingual sentence encoder covering 80 languages.

Model checkpoint: facebook/MEXMA

7. Self-Taught Evaluator: a new method for generating synthetic preference data to train reward models without relying on human annotations.

Model checkpoint: facebook/Self-taught-evaluator-llama3.1-70B

8. Meta Spirit LM: An open-source language model for seamless speech and text integration.

Repo:https://github.com/facebookresearch/spiritlm
  • 2 replies
·
erinys
posted anupdate 1 day ago
m-ric
posted anupdate 1 day ago
view post
Post
1327
By far the coolest release of the day!
> The Open LLM Leaderboard, most comprehensive suite for comparing Open LLMs on many benchmarks, just released a comparator tool that lets you dig into the detail of differences between any models.

Here's me checking how the new Llama-3.1-Nemotron-70B that we've heard so much compares to the original Llama-3.1-70B. 🤔🔎

Try it out here 👉 open-llm-leaderboard/comparator
  • 2 replies
·
albertvillanova
posted anupdate 1 day ago
view post
Post
1591
🚨 We’ve just released a new tool to compare the performance of models in the 🤗 Open LLM Leaderboard: the Comparator 🎉
open-llm-leaderboard/comparator

Want to see how two different versions of LLaMA stack up? Let’s walk through a step-by-step comparison of LLaMA-3.1 and LLaMA-3.2. 🦙🧵👇

1/ Load the Models' Results
- Go to the 🤗 Open LLM Leaderboard Comparator: open-llm-leaderboard/comparator
- Search for "LLaMA-3.1" and "LLaMA-3.2" in the model dropdowns.
- Press the Load button. Ready to dive into the results!

2/ Compare Metric Results in the Results Tab 📊
- Head over to the Results tab.
- Here, you’ll see the performance metrics for each model, beautifully color-coded using a gradient to highlight performance differences: greener is better! 🌟
- Want to focus on a specific task? Use the Task filter to hone in on comparisons for tasks like BBH or MMLU-Pro.

3/ Check Config Alignment in the Configs Tab ⚙️
- To ensure you’re comparing apples to apples, head to the Configs tab.
- Review both models’ evaluation configurations, such as metrics, datasets, prompts, few-shot configs...
- If something looks off, it’s good to know before drawing conclusions! ✅

4/ Compare Predictions by Sample in the Details Tab 🔍
- Curious about how each model responds to specific inputs? The Details tab is your go-to!
- Select a Task (e.g., MuSR) and then a Subtask (e.g., Murder Mystery) and then press the Load Details button.
- Check out the side-by-side predictions and dive into the nuances of each model’s outputs.

5/ With this tool, it’s never been easier to explore how small changes between model versions affect performance on a wide range of tasks. Whether you’re a researcher or enthusiast, you can instantly visualize improvements and dive into detailed comparisons.

🚀 Try the 🤗 Open LLM Leaderboard Comparator now and take your model evaluations to the next level!
victor
posted anupdate 2 days ago
merve
posted anupdate about 18 hours ago
view post
Post
606
It's raining depth estimation models ☔️
DepthPro is a zero-shot depth estimation model by Apple, it's fast, sharp and accurate 🔥
Demo: akhaliq/depth-pro
Model: apple/DepthPro
Paper page: Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (2410.02073)

The model consists of two encoders: an encoder for patches and an image encoder 🖼️ The outputs of both are merged to decode to depth maps and get the focal length.
The model outperforms the previous state-of-the-art models in average of various benchmarks 📑
ImranzamanML
posted anupdate 1 day ago
view post
Post
664
Here is how we can calculate the size of any LLM model:

Each parameter in LLM models is typically stored as a floating-point number. The size of each parameter in bytes depends on the precision.

32-bit precision: Each parameter takes 4 bytes.
16-bit precision: Each parameter takes 2 bytes

To calculate the total memory usage of the model:
Memory usage (in bytes) = No. of Parameters × Size of Each Parameter

For example:
32-bit Precision (FP32)
In 32-bit floating-point precision, each parameter takes 4 bytes.
Memory usage in bytes = 1 billion parameters × 4 bytes
1,000,000,000 × 4 = 4,000,000,000 bytes
In gigabytes: ≈ 3.73 GB

16-bit Precision (FP16)
In 16-bit floating-point precision, each parameter takes 2 bytes.
Memory usage in bytes = 1 billion parameters × 2 bytes
1,000,000,000 × 2 = 2,000,000,000 bytes
In gigabytes: ≈ 1.86 GB

It depends on whether you use 32-bit or 16-bit precision, a model with 1 billion parameters would use approximately 3.73 GB or 1.86 GB of memory, respectively.
nroggendorff
posted anupdate 1 day ago
view post
Post
955
100 followers? When did that happen?
Recently active users